Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when maker projects work on USB bench power but fail on their intended supply path, especially for WiFi or sensor-heavy boards such as ESP32, including brownout, current-peak, regulator, and wiring-path diagnosis.
Fully automated migration of Field Service Mobile flows (processType='FieldServiceMobile') to DataCaptureFlow. Retrieves flow XML from the org, runs a transformer script to restructure the execution graph and convert all field types, deploys the migrated flow as Draft only (activation is always a separate manual admin step after validation), and reports functional-equivalence differences. Handles most flows end-to-end without manual intervention. Always use this skill even for changes that look trivial, like removing one component or reordering one element — Data Capture's runtime behaves differently from Flow Builder previews, in ways only the transformer script accounts for. Use when a user wants to migrate, modernize, convert, audit, or replace legacy Field Service Mobile flow `.flow` / `.flow-meta.xml` files with Data Capture, or assess migration readiness. Do not use to edit an existing Data Capture flow or author a new one from scratch — covers only the one-time legacy migration.
This skill should be used when the user asks to "find papers", "search for papers", "what does the literature say", "find research on", "academic papers about", "literature review", "cite papers", or needs to answer questions using academic literature.
Performs a structured firewall rule base audit against CIS Controls v8 (Controls 4.4 and 4.5) and NIST SP 800-41 Rev 1 (Guidelines on Firewalls and Firewall Policy). Auto-invoked when reviewing firewall configurations, ACLs, or network security policies. Produces a prioritized findings report covering overly permissive rules, shadowed rules, logging gaps, and egress filtering deficiencies.
Break any problem down to fundamental truths, then rebuild solutions from atoms up. Use when user says "firstp", "first principles", "from scratch", "what are we assuming", "break this down", "atomic", "fundamental truth", "physics thinking", "Elon method", "bedrock", "ground up", "core problem", "strip away", or challenges assumptions about how things are done.
Use the minimal FlareSolverr wrapper for a one-off health check or browser-backed GET/POST when ordinary retrieval is blocked by Cloudflare or DDoS-GUARD. Choose flaresolverr-cli instead for named session lifecycle, cookie-only returns, dry-run planning, or the full operational command surface. Do not use this skill for unrelated requests; route to the nearest named specialist.
Implement or repair Flutter local notifications and remote push delivery across permission, scheduling, token, lifecycle, payload, interaction, and reconciliation flows. Use for notification behavior; route ordinary API transport, navigation, persistence, and custom native bridge work to their specialists.
Use when designing OData queries, datasources, flows, or reports that touch Footprint WMS data — i.e. anything querying entities like Tasks, Shipments, ArchivedShippingLicensePlateContents (ASLPC), LicensePlate, Lot, Material, Project, Owner, or any Footprint operational concept (receiving, shipping, inventory archive, license plates, fixed/catch weight, packaging). Captures the navigation chains, filter conventions, weight calculations, and exclusion rules that the OData metadata alone doesn't reveal. Use BEFORE building a flow datasource over a Footprint entity. Skip for non-Footprint apps (custom apps with no WMS data).
Write minimal, accessible web UI without over-engineering, adapting to whatever stack the project uses — React, Vue, Svelte, Angular, web components, or plain HTML. Use this skill on every project and every task that writes or reviews markup or components, builds forms, adds interactive elements like buttons, dialogs, accordions, or tabs, or audits code for accessibility — even when the user never mentions accessibility, and even inside a framework, CMS, or design system. It's non-negotiable regardless of project type, stack, or deadline. About to reach for ARIA attributes, a dialog library, a focus-trap package, or a headless UI component? Use this skill first.
Guides an AI to implement a single-symbol base-price grid program on Futu OpenAPI: validate six parameters first, then write a restart-safe limit-order reconciliation loop and accept it on a paper account. Use when the user wants a grid strategy, grid program, quantitative grid, or grid trading bot, or says 网格策略、网格程序、量化网格、网格交易机器人、实现网格 or 帮我写一个网格. Request fields follow the OpenAPI llms.md. This skill does not repeat request bodies. Paper account by default.
Performs a GCP security posture review against the CIS Google Cloud Platform Foundation Benchmark v2.0.0. Auto-invoked when reviewing GCP infrastructure, IAM bindings, VPC firewall rules, Cloud Audit Logs, or GCS bucket security. Walks through all seven benchmark sections, evaluates each recommendation, and produces a prioritized findings report with remediation guidance mapped to specific CIS control IDs.
Audit and optimize content for SEO, GEO (generative engine optimization), and AEO (answer engine optimization). Use when user asks to "audit SEO", "check search visibility", "optimize for AI search", "generate schema markup", "validate metadata", "extract keywords", "optimize for Perplexity/ChatGPT/Gemini", "check Open Graph tags", "submit to IndexNow", or mentions SEO, GEO, AEO, or search optimization. Do NOT use for creating new content from scratch or image optimization.
Branching, merging, versioning, and release conventions for the Gitflow workflow, covering main/develop branches, feature/release/hotfix branches, semantic versioning, and pull request rules. Use when creating a branch, naming a branch, planning a release or hotfix, writing a commit message, or setting up branch protection for a repository that follows Gitflow.
Plan and evaluate go-to-market strategy using positioning, acquisition, growth economics, market-entry, competitive-response, and governed agent-assisted acquisition experiments. Use for ICP, customer-centered messaging, website narrative, outcome-linked operating partnerships, channel, CAC/LTV, beachhead, or automated-GTM strategy decisions. Do not use for campaign execution, CRM mutations, legal interpretation, product strategy, or visual brand design
Build or review Next.js App Router animation: GSAP page transitions, component enter/exit, scroll effects, interrupted motion, and cleanup. Use even when GSAP is unnamed, including choosing React View Transitions. Also covers loading flashes, data-ready entrances, layout stability, hidden-content recovery, and first-load performance. Not for Pages Router, other routers, or isolated GSAP API questions.
Google Guava best-practice patterns distilled from the official wiki, covering the of/copyOf/builder patterns for immutable collections and defensive copy rules, deciding between LoadingCache, Cache and Caffeine, immutable Joiner/Splitter pipelines, CharMatcher instead of regex, Preconditions with formatted messages, and CaseFormat name conversion. Corrects common LLM misuse: hand-rolled immutable collections, ConcurrentHashMap instead of Cache, unawareness of CharMatcher.
Use when you need to visually interact with a GUI: test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Needs the `cua` CLI (curl -fsSL https://cua.ai/install.sh | sh).
Getting ROI from hackathon sponsorships for developer tools. Covers evaluating which hackathons to sponsor, booth presence strategies, prizes that actually work, judge involvement, follow-up strategies, and measuring sponsorship ROI. Use when asked about: - Hackathon sponsorship strategy - Developer event sponsorship ROI - Hackathon prizes - Booth presence at hackathons - Post-hackathon follow-up - Hackathon sponsorship evaluation
Use when adding, modifying, or removing toolbar buttons and click flows on a Datex Studio hub configuration. Covers fetching hub config via `dxs configuration get hub`, editing the toolbar[] and flows[] arrays, wiring click flows that launch reports, and pushing the modified config back with `dxs configuration upsert hub`. Trigger for: "add a toolbar button to the X hub", "wire a button that opens the Y report", "modify hub N", "change what the X button does", "launch report Y from a hub button".
This skill MUST be used by default for any user-facing writing, including answers to users, emails, documents, formal correspondence, reports, proposals, rules, prompts, skill instructions, project introductions, README files, repository descriptions, landing-page copy, social posts, essays, commentary, explanations, summaries, product copy, internal updates, and other prose intended to be read by people. Apply it whenever the output contains human-readable text. This skill MUST NOT be skipped unless another skill explicitly owns the writing style or the output is purely code, structured data, or a command. Supports Chinese and English
Diagnose NCCL failures and adjacent training-pod failures on HyperPod GPU clusters (EKS or Slurm) — training hangs, AllReduce / collective-op timeouts, EFA or libfabric errors, rendezvous failures, EFA TCP fallback, /dev/shm or memlock issues, NCCL version mismatch across pods, container OOM / exit-137 / OOMKilled, GPU OOM (CUDA out of memory), CrashLoopBackOff / Pending pods, MASTER_ADDR DNS, NetworkPolicy blocking. Not for single-node hardware faults (→ hyperpod-node-debugger § G) or cluster-creation EFA / SSM failures (→ hyperpod-cluster-debugger § A / § F).
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. Covers on-node EFA, GPU / accelerator hardware (XID, ECC, NVLink, row-remap, DCGM), Slurm node down/drained, disk and memory pressure, per-node lifecycle-script failures, SSM agent, container runtime, kernel panics, pod networking. Read-only. Not for cluster-wide provisioning (→ hyperpod-cluster-debugger), NCCL (→ hyperpod-nccl), or MFU (→ hyperpod-mfu-debugger).
Diagnostic-only skill for Slurm scheduler and node-daemon issues on Amazon SageMaker HyperPod Slurm clusters. Scope mirrors the HyperPod troubleshooting guide. Invoke when the user reports a Slurm node stuck in down/drain, "Node unexpectedly rebooted" after auto-repair, slurmd not running, jobs stuck PENDING with REASON=Resources while sinfo shows idle nodes, jobs stuck COMPLETING after node replacement, GRES/GPU counts wrong, scontrol ping failing, slurmctld unresponsive, an Action:Reboot/Replace request that did not trigger HyperPod auto-recovery, or auto-resume not restarting a job. Also triggers on "drain before reboot", "diagnose a Slurm node", "investigate stuck jobs."
Configures GitHub Advanced Security (code scanning with CodeQL, secret scanning, dependency review, and Dependabot alerts) to perform automated static analysis and vulnerability detection across repositories at enterprise scale, including custom CodeQL queries and CI workflow integration. Use when setting up or tuning code scanning, rolling out CodeQL across an organization, or shifting SAST left into pull request workflows.
Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin manager (ov-install as backup), wizard-based configuration, slot activation, gateway restart, verification, multi-tenant root keys, multi-instance and uninstall. The user needs no CLI knowledge — the agent runs everything and only asks for a few values. Assumes the OpenViking server is already running; it does NOT install the server. Trigger on: "install OpenViking", "set up memory", "configure memory plugin", "add long-term memory", "semantic memory", "RAG", "帮我装 OpenViking", "配置记忆插件", "安装记忆功能", "接入 OpenViking".
Assists judges in making structured, reviewable and defensible judicial value judgments in scenarios of conflicting rights, legal uncertainty, proportionality review and reasoned discretion. This Skill helps judges identify conflicts of legal values in hard cases, determine the boundaries of discretion, carry out value balancing, and form an analytical framework usable for judicial reasoning. It does not replace the judge's final ruling; instead, it helps judges translate value judgments into a judicial reasoning process grounded in facts, norms and argumentative structure.
Give first-time users a short, value-first Kitaru tour with the PydanticAI returns agent example in the Kitaru repository. Use when someone has no agent or traces of their own, arrives from Kitaru onboarding, asks for a demo, tutorial, quickstart, or guided example, needs the quickstart example cloned or prepared, wants the coding agent to prepare trace annotations before they judge sessions, or wants to experience Kitaru's value before learning the full investigation method. Prepare a three-session frontend review, let the human provide verdicts, turn one accepted finding into a deterministic evaluator, and finish with one approved bounded replay experiment. Route real agents, open-ended discovery, and production evidence to kitaru-investigation instead.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.